Online Learning with Feedback Graphs Without the Graphs release_uivua4t5rrhxdbulm3etzm5uha

by Alon Cohen, Tamir Hazan, Tomer Koren

Released as a article .

2016  

Abstract

We study an online learning framework introduced by Mannor and Shamir (2011) in which the feedback is specified by a graph, in a setting where the graph may vary from round to round and is never fully revealed to the learner. We show a large gap between the adversarial and the stochastic cases. In the adversarial case, we prove that even for dense feedback graphs, the learner cannot improve upon a trivial regret bound obtained by ignoring any additional feedback besides her own loss. In contrast, in the stochastic case we give an algorithm that achieves Θ(√(α T)) regret over T rounds, provided that the independence numbers of the hidden feedback graphs are at most α. We also extend our results to a more general feedback model, in which the learner does not necessarily observe her own loss, and show that, even in simple cases, concealing the feedback graphs might render a learnable problem unlearnable.
In text/plain format

Archived Files and Locations

application/pdf  244.6 kB
file_vcem6itjfzespor52crpgbmpke
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2016-05-23
Version   v1
Language   en ?
arXiv  1605.07018v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 8c98c6ae-9f13-4c41-9b90-c4458079e2c4
API URL: JSON